ssdataanalysis commited on
Commit
86d68b6
·
verified ·
1 Parent(s): d387765

Clear repo before clean re-upload

Browse files
README.md DELETED
@@ -1,36 +0,0 @@
1
- ---
2
- license: apache-2.0
3
- license_name: jamba-open-model-license
4
- license_link: https://www.ai21.com/licenses/jamba-open-model-license
5
- pipeline_tag: text-generation
6
- library_name: transformers
7
- base_model: ai21labs/AI21-Jamba-Reasoning-3B
8
- tags:
9
- - mlx
10
- ---
11
-
12
- # ssdataanalysis/AI21-Jamba-Reasoning-3B-mlx-fp16
13
-
14
- The Model [ssdataanalysis/AI21-Jamba-Reasoning-3B-mlx-fp16](https://huggingface.co/ssdataanalysis/AI21-Jamba-Reasoning-3B-mlx-fp16) was converted to MLX format from [ai21labs/AI21-Jamba-Reasoning-3B](https://huggingface.co/ai21labs/AI21-Jamba-Reasoning-3B) using mlx-lm version **0.29.1**.
15
-
16
- ## Use with mlx
17
-
18
- ```bash
19
- pip install mlx-lm
20
- ```
21
-
22
- ```python
23
- from mlx_lm import load, generate
24
-
25
- model, tokenizer = load("ssdataanalysis/AI21-Jamba-Reasoning-3B-mlx-fp16")
26
-
27
- prompt="hello"
28
-
29
- if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
30
- messages = [{"role": "user", "content": prompt}]
31
- prompt = tokenizer.apply_chat_template(
32
- messages, tokenize=False, add_generation_prompt=True
33
- )
34
-
35
- response = generate(model, tokenizer, prompt=prompt, verbose=True)
36
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
chat_template.jinja DELETED
@@ -1,101 +0,0 @@
1
-
2
- {%- set thinking_prefix = thinking_prefix or 'Begin by thinking about the reasoning process in the mind within <think> </think> tags and then proceed to give your response.\n' -%}
3
-
4
- {%- if bos_token is defined and bos_token is not none %}{{- bos_token -}}{%- endif %}
5
- {%- if tools %}
6
- {{- '<|im_start|>system\n' }}
7
- {%- if messages|length > 0 and messages[0].role == 'system' %}
8
- {{- messages[0].content + '\n\n' }}
9
- {%- endif %}
10
- {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
11
- {%- for tool in tools %}
12
- {{- "\n" }}
13
- {{- tool | tojson }}
14
- {%- endfor %}
15
- {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
16
- {%- else %}
17
- {%- if messages|length > 0 and messages[0].role == 'system' %}
18
- {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
19
- {%- endif %}
20
- {%- endif %}
21
- {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
22
- {%- for message in messages[::-1] %}
23
- {%- set index = (messages|length - 1) - loop.index0 %}
24
- {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
25
- {%- set ns.multi_step_tool = false %}
26
- {%- set ns.last_query_index = index %}
27
- {%- endif %}
28
- {%- endfor %}
29
- {%- for message in messages %}
30
- {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
31
- {%- set prefix = '' %}
32
- {%- if message.role == 'user' and '<think>' not in message.content %}
33
- {%- if loop.last %}
34
- {%- set prefix = thinking_prefix %}
35
- {%- endif %}
36
- {%- if not loop.last %}
37
- {%- if loop.nextitem.role == 'assistant' and loop.nextitem.content.startswith('<think>') or loop.nextitem.reasoning_content is defined and loop.nextitem.reasoning_content is not none %}
38
- {%- set prefix = thinking_prefix %}
39
- {%- endif %}
40
- {%- endif %}
41
- {%- endif %}
42
- {%- if message.role == 'user' and not loop.last and loop.nextitem.role == 'assistant' and loop.nextitem.content.startswith('<think>') and '<think>' not in message.content %}
43
- {%- set prefix = thinking_prefix %}
44
- {%- endif %}
45
- {{- '<|im_start|>' + message.role + '\n' + prefix + message.content + '<|im_end|>' + '\n' }}
46
- {%- elif message.role == "assistant" %}
47
- {%- set content = message.content %}
48
- {%- set reasoning_content = '' %}
49
- {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
50
- {%- set reasoning_content = message.reasoning_content %}
51
- {%- else %}
52
- {%- if '</think>' in message.content %}
53
- {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
54
- {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
55
- {%- endif %}
56
- {%- endif %}
57
- {%- if loop.index0 > ns.last_query_index %}
58
- {%- if reasoning_content %}
59
- {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
60
- {%- else %}
61
- {{- '<|im_start|>' + message.role + '\n' + content }}
62
- {%- endif %}
63
- {%- else %}
64
- {{- '<|im_start|>' + message.role + '\n' + content }}
65
- {%- endif %}
66
- {%- if message.tool_calls %}
67
- {%- for tool_call in message.tool_calls %}
68
- {%- if (loop.first and content) or (not loop.first) %}
69
- {{- '\n' }}
70
- {%- endif %}
71
- {%- if tool_call.function %}
72
- {%- set tool_call = tool_call.function %}
73
- {%- endif %}
74
- {{- '<tool_call>\n{"name": "' }}
75
- {{- tool_call.name }}
76
- {{- '", "arguments": ' }}
77
- {%- if tool_call.arguments is string %}
78
- {{- tool_call.arguments }}
79
- {%- else %}
80
- {{- tool_call.arguments | tojson }}
81
- {%- endif %}
82
- {{- '}\n</tool_call>' }}
83
- {%- endfor %}
84
- {%- endif %}
85
- {{- '<|im_end|>\n' }}
86
- {%- elif message.role == "tool" %}
87
- {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
88
- {{- '<|im_start|>user' }}
89
- {%- endif %}
90
- {{- '\n<tool_response>\n' }}
91
- {{- message.content }}
92
- {{- '\n</tool_response>' }}
93
- {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
94
- {{- '<|im_end|>\n' }}
95
- {%- endif %}
96
- {%- endif %}
97
- {%- endfor %}
98
- {%- if add_generation_prompt %}
99
- {{- '<|im_start|>assistant\n' }}
100
- {{- '<think>\n' }}
101
- {%- endif -%}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json DELETED
@@ -1,44 +0,0 @@
1
- {
2
- "architectures": [
3
- "JambaForCausalLM"
4
- ],
5
- "attention_dropout": 0.0,
6
- "attn_layer_offset": 7,
7
- "attn_layer_period": 14,
8
- "bos_token_id": 1,
9
- "dtype": "bfloat16",
10
- "eos_token_id": [
11
- 2,
12
- 519
13
- ],
14
- "expert_layer_offset": 1,
15
- "expert_layer_period": 2,
16
- "hidden_act": "silu",
17
- "hidden_size": 2560,
18
- "initializer_range": 0.02,
19
- "intermediate_size": 8192,
20
- "mamba_conv_bias": true,
21
- "mamba_d_conv": 4,
22
- "mamba_d_state": 16,
23
- "mamba_dt_rank": 160,
24
- "mamba_expand": 2,
25
- "mamba_proj_bias": false,
26
- "max_position_embeddings": 262144,
27
- "model_type": "jamba",
28
- "num_attention_heads": 20,
29
- "num_experts": 1,
30
- "num_experts_per_tok": 1,
31
- "num_hidden_layers": 28,
32
- "num_key_value_heads": 1,
33
- "num_logits_to_keep": 1,
34
- "output_router_logits": false,
35
- "pad_token_id": 0,
36
- "rms_norm_eps": 1e-06,
37
- "router_aux_loss_coef": 0.001,
38
- "sliding_window": null,
39
- "tie_word_embeddings": true,
40
- "transformers_version": "4.56.1",
41
- "use_cache": true,
42
- "use_mamba_kernels": true,
43
- "vocab_size": 65536
44
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
generation_config.json DELETED
@@ -1,8 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 519,
5
- "pad_token_id": 0,
6
- "transformers_version": "4.56.1",
7
- "temparature": 0.6
8
- }
 
 
 
 
 
 
 
 
 
model-00001-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:76c7d804bdbfd98bc478d4dfa3d284841088e176fd13b69e317a1e7ef1de43e1
3
- size 5349849861
 
 
 
 
model-00002-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a703c814b016a69c6f53a7b46ddf282ab7321d5e1df983320ab3c43623661ad7
3
- size 708876429
 
 
 
 
model.safetensors.index.json DELETED
@@ -1,470 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 6058674944,
4
- "total_parameters": 3027074432
5
- },
6
- "weight_map": {
7
- "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
- "model.final_layernorm.weight": "model-00002-of-00002.safetensors",
9
- "model.layers.0.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
10
- "model.layers.0.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
11
- "model.layers.0.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
12
- "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
13
- "model.layers.0.mamba.A_log": "model-00001-of-00002.safetensors",
14
- "model.layers.0.mamba.D": "model-00001-of-00002.safetensors",
15
- "model.layers.0.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
16
- "model.layers.0.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
17
- "model.layers.0.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
18
- "model.layers.0.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
19
- "model.layers.0.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
20
- "model.layers.0.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
21
- "model.layers.0.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
22
- "model.layers.0.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
23
- "model.layers.0.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
24
- "model.layers.0.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
25
- "model.layers.0.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
26
- "model.layers.1.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
27
- "model.layers.1.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
28
- "model.layers.1.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
29
- "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
30
- "model.layers.1.mamba.A_log": "model-00001-of-00002.safetensors",
31
- "model.layers.1.mamba.D": "model-00001-of-00002.safetensors",
32
- "model.layers.1.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
33
- "model.layers.1.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
34
- "model.layers.1.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
35
- "model.layers.1.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
36
- "model.layers.1.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
37
- "model.layers.1.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
38
- "model.layers.1.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
39
- "model.layers.1.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
40
- "model.layers.1.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
41
- "model.layers.1.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
42
- "model.layers.1.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
43
- "model.layers.10.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
44
- "model.layers.10.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
45
- "model.layers.10.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
46
- "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
47
- "model.layers.10.mamba.A_log": "model-00001-of-00002.safetensors",
48
- "model.layers.10.mamba.D": "model-00001-of-00002.safetensors",
49
- "model.layers.10.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
50
- "model.layers.10.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
51
- "model.layers.10.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
52
- "model.layers.10.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
53
- "model.layers.10.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
54
- "model.layers.10.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
55
- "model.layers.10.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
56
- "model.layers.10.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
57
- "model.layers.10.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
58
- "model.layers.10.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
59
- "model.layers.10.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
60
- "model.layers.11.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
61
- "model.layers.11.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
62
- "model.layers.11.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
63
- "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
64
- "model.layers.11.mamba.A_log": "model-00001-of-00002.safetensors",
65
- "model.layers.11.mamba.D": "model-00001-of-00002.safetensors",
66
- "model.layers.11.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
67
- "model.layers.11.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
68
- "model.layers.11.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
69
- "model.layers.11.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
70
- "model.layers.11.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
71
- "model.layers.11.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
72
- "model.layers.11.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
73
- "model.layers.11.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
74
- "model.layers.11.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
75
- "model.layers.11.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
76
- "model.layers.11.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
77
- "model.layers.12.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
78
- "model.layers.12.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
79
- "model.layers.12.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
80
- "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
- "model.layers.12.mamba.A_log": "model-00001-of-00002.safetensors",
82
- "model.layers.12.mamba.D": "model-00001-of-00002.safetensors",
83
- "model.layers.12.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
84
- "model.layers.12.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
85
- "model.layers.12.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
86
- "model.layers.12.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
87
- "model.layers.12.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
88
- "model.layers.12.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
89
- "model.layers.12.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
90
- "model.layers.12.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
91
- "model.layers.12.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
92
- "model.layers.12.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
93
- "model.layers.12.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
94
- "model.layers.13.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
95
- "model.layers.13.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
96
- "model.layers.13.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
97
- "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
98
- "model.layers.13.mamba.A_log": "model-00001-of-00002.safetensors",
99
- "model.layers.13.mamba.D": "model-00001-of-00002.safetensors",
100
- "model.layers.13.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
101
- "model.layers.13.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
102
- "model.layers.13.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
103
- "model.layers.13.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
104
- "model.layers.13.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
105
- "model.layers.13.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
106
- "model.layers.13.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
107
- "model.layers.13.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
108
- "model.layers.13.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
109
- "model.layers.13.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
110
- "model.layers.13.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
111
- "model.layers.14.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
112
- "model.layers.14.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
113
- "model.layers.14.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
114
- "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
115
- "model.layers.14.mamba.A_log": "model-00001-of-00002.safetensors",
116
- "model.layers.14.mamba.D": "model-00001-of-00002.safetensors",
117
- "model.layers.14.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
118
- "model.layers.14.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
119
- "model.layers.14.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
120
- "model.layers.14.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
121
- "model.layers.14.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
122
- "model.layers.14.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
123
- "model.layers.14.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
124
- "model.layers.14.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
125
- "model.layers.14.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
126
- "model.layers.14.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
127
- "model.layers.14.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
128
- "model.layers.15.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
129
- "model.layers.15.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
130
- "model.layers.15.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
131
- "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
132
- "model.layers.15.mamba.A_log": "model-00001-of-00002.safetensors",
133
- "model.layers.15.mamba.D": "model-00001-of-00002.safetensors",
134
- "model.layers.15.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
135
- "model.layers.15.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
136
- "model.layers.15.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
137
- "model.layers.15.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
138
- "model.layers.15.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
139
- "model.layers.15.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
140
- "model.layers.15.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
141
- "model.layers.15.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
142
- "model.layers.15.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
143
- "model.layers.15.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
144
- "model.layers.15.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
145
- "model.layers.16.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
146
- "model.layers.16.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
147
- "model.layers.16.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
148
- "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
149
- "model.layers.16.mamba.A_log": "model-00001-of-00002.safetensors",
150
- "model.layers.16.mamba.D": "model-00001-of-00002.safetensors",
151
- "model.layers.16.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
152
- "model.layers.16.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
153
- "model.layers.16.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
154
- "model.layers.16.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
155
- "model.layers.16.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
156
- "model.layers.16.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
157
- "model.layers.16.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
158
- "model.layers.16.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
159
- "model.layers.16.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
160
- "model.layers.16.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
161
- "model.layers.16.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
162
- "model.layers.17.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
163
- "model.layers.17.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
164
- "model.layers.17.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
165
- "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
166
- "model.layers.17.mamba.A_log": "model-00001-of-00002.safetensors",
167
- "model.layers.17.mamba.D": "model-00001-of-00002.safetensors",
168
- "model.layers.17.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
169
- "model.layers.17.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
170
- "model.layers.17.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
171
- "model.layers.17.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
172
- "model.layers.17.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
173
- "model.layers.17.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
174
- "model.layers.17.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
175
- "model.layers.17.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
176
- "model.layers.17.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
177
- "model.layers.17.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
178
- "model.layers.17.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
179
- "model.layers.18.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
180
- "model.layers.18.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
181
- "model.layers.18.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
182
- "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
183
- "model.layers.18.mamba.A_log": "model-00001-of-00002.safetensors",
184
- "model.layers.18.mamba.D": "model-00001-of-00002.safetensors",
185
- "model.layers.18.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
186
- "model.layers.18.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
187
- "model.layers.18.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
188
- "model.layers.18.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
189
- "model.layers.18.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
190
- "model.layers.18.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
191
- "model.layers.18.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
192
- "model.layers.18.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
193
- "model.layers.18.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
194
- "model.layers.18.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
195
- "model.layers.18.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
196
- "model.layers.19.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
197
- "model.layers.19.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
198
- "model.layers.19.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
199
- "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
200
- "model.layers.19.mamba.A_log": "model-00001-of-00002.safetensors",
201
- "model.layers.19.mamba.D": "model-00001-of-00002.safetensors",
202
- "model.layers.19.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
203
- "model.layers.19.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
204
- "model.layers.19.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
205
- "model.layers.19.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
206
- "model.layers.19.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
207
- "model.layers.19.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
208
- "model.layers.19.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
209
- "model.layers.19.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
210
- "model.layers.19.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
211
- "model.layers.19.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
212
- "model.layers.19.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
213
- "model.layers.2.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
214
- "model.layers.2.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
215
- "model.layers.2.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
216
- "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
217
- "model.layers.2.mamba.A_log": "model-00001-of-00002.safetensors",
218
- "model.layers.2.mamba.D": "model-00001-of-00002.safetensors",
219
- "model.layers.2.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
220
- "model.layers.2.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
221
- "model.layers.2.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
222
- "model.layers.2.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
223
- "model.layers.2.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
224
- "model.layers.2.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
225
- "model.layers.2.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
226
- "model.layers.2.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
227
- "model.layers.2.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
228
- "model.layers.2.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
229
- "model.layers.2.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
230
- "model.layers.20.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
231
- "model.layers.20.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
232
- "model.layers.20.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
233
- "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
234
- "model.layers.20.mamba.A_log": "model-00001-of-00002.safetensors",
235
- "model.layers.20.mamba.D": "model-00001-of-00002.safetensors",
236
- "model.layers.20.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
237
- "model.layers.20.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
238
- "model.layers.20.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
239
- "model.layers.20.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
240
- "model.layers.20.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
241
- "model.layers.20.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
242
- "model.layers.20.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
243
- "model.layers.20.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
244
- "model.layers.20.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
245
- "model.layers.20.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
246
- "model.layers.20.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
247
- "model.layers.21.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
248
- "model.layers.21.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
249
- "model.layers.21.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
250
- "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
251
- "model.layers.21.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
252
- "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
253
- "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
254
- "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
255
- "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
256
- "model.layers.22.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
257
- "model.layers.22.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
258
- "model.layers.22.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
259
- "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
260
- "model.layers.22.mamba.A_log": "model-00001-of-00002.safetensors",
261
- "model.layers.22.mamba.D": "model-00001-of-00002.safetensors",
262
- "model.layers.22.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
263
- "model.layers.22.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
264
- "model.layers.22.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
265
- "model.layers.22.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
266
- "model.layers.22.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
267
- "model.layers.22.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
268
- "model.layers.22.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
269
- "model.layers.22.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
270
- "model.layers.22.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
271
- "model.layers.22.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
272
- "model.layers.22.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
273
- "model.layers.23.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
274
- "model.layers.23.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
275
- "model.layers.23.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
276
- "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
277
- "model.layers.23.mamba.A_log": "model-00001-of-00002.safetensors",
278
- "model.layers.23.mamba.D": "model-00001-of-00002.safetensors",
279
- "model.layers.23.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
280
- "model.layers.23.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
281
- "model.layers.23.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
282
- "model.layers.23.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
283
- "model.layers.23.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
284
- "model.layers.23.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
285
- "model.layers.23.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
286
- "model.layers.23.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
287
- "model.layers.23.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
288
- "model.layers.23.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
289
- "model.layers.23.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
290
- "model.layers.24.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
291
- "model.layers.24.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
292
- "model.layers.24.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
293
- "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
294
- "model.layers.24.mamba.A_log": "model-00001-of-00002.safetensors",
295
- "model.layers.24.mamba.D": "model-00001-of-00002.safetensors",
296
- "model.layers.24.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
297
- "model.layers.24.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
298
- "model.layers.24.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
299
- "model.layers.24.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
300
- "model.layers.24.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
301
- "model.layers.24.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
302
- "model.layers.24.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
303
- "model.layers.24.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
304
- "model.layers.24.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
305
- "model.layers.24.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
306
- "model.layers.24.pre_ff_layernorm.weight": "model-00002-of-00002.safetensors",
307
- "model.layers.25.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
308
- "model.layers.25.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
309
- "model.layers.25.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
310
- "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
311
- "model.layers.25.mamba.A_log": "model-00002-of-00002.safetensors",
312
- "model.layers.25.mamba.D": "model-00002-of-00002.safetensors",
313
- "model.layers.25.mamba.b_layernorm.weight": "model-00002-of-00002.safetensors",
314
- "model.layers.25.mamba.c_layernorm.weight": "model-00002-of-00002.safetensors",
315
- "model.layers.25.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
316
- "model.layers.25.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
317
- "model.layers.25.mamba.dt_layernorm.weight": "model-00002-of-00002.safetensors",
318
- "model.layers.25.mamba.dt_proj.bias": "model-00002-of-00002.safetensors",
319
- "model.layers.25.mamba.dt_proj.weight": "model-00002-of-00002.safetensors",
320
- "model.layers.25.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
321
- "model.layers.25.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
322
- "model.layers.25.mamba.x_proj.weight": "model-00002-of-00002.safetensors",
323
- "model.layers.25.pre_ff_layernorm.weight": "model-00002-of-00002.safetensors",
324
- "model.layers.26.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
325
- "model.layers.26.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
326
- "model.layers.26.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
327
- "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
328
- "model.layers.26.mamba.A_log": "model-00002-of-00002.safetensors",
329
- "model.layers.26.mamba.D": "model-00002-of-00002.safetensors",
330
- "model.layers.26.mamba.b_layernorm.weight": "model-00002-of-00002.safetensors",
331
- "model.layers.26.mamba.c_layernorm.weight": "model-00002-of-00002.safetensors",
332
- "model.layers.26.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
333
- "model.layers.26.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
334
- "model.layers.26.mamba.dt_layernorm.weight": "model-00002-of-00002.safetensors",
335
- "model.layers.26.mamba.dt_proj.bias": "model-00002-of-00002.safetensors",
336
- "model.layers.26.mamba.dt_proj.weight": "model-00002-of-00002.safetensors",
337
- "model.layers.26.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
338
- "model.layers.26.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
339
- "model.layers.26.mamba.x_proj.weight": "model-00002-of-00002.safetensors",
340
- "model.layers.26.pre_ff_layernorm.weight": "model-00002-of-00002.safetensors",
341
- "model.layers.27.feed_forward.down_proj.weight": "model-00002-of-00002.safetensors",
342
- "model.layers.27.feed_forward.gate_proj.weight": "model-00002-of-00002.safetensors",
343
- "model.layers.27.feed_forward.up_proj.weight": "model-00002-of-00002.safetensors",
344
- "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
345
- "model.layers.27.mamba.A_log": "model-00002-of-00002.safetensors",
346
- "model.layers.27.mamba.D": "model-00002-of-00002.safetensors",
347
- "model.layers.27.mamba.b_layernorm.weight": "model-00002-of-00002.safetensors",
348
- "model.layers.27.mamba.c_layernorm.weight": "model-00002-of-00002.safetensors",
349
- "model.layers.27.mamba.conv1d.bias": "model-00002-of-00002.safetensors",
350
- "model.layers.27.mamba.conv1d.weight": "model-00002-of-00002.safetensors",
351
- "model.layers.27.mamba.dt_layernorm.weight": "model-00002-of-00002.safetensors",
352
- "model.layers.27.mamba.dt_proj.bias": "model-00002-of-00002.safetensors",
353
- "model.layers.27.mamba.dt_proj.weight": "model-00002-of-00002.safetensors",
354
- "model.layers.27.mamba.in_proj.weight": "model-00002-of-00002.safetensors",
355
- "model.layers.27.mamba.out_proj.weight": "model-00002-of-00002.safetensors",
356
- "model.layers.27.mamba.x_proj.weight": "model-00002-of-00002.safetensors",
357
- "model.layers.27.pre_ff_layernorm.weight": "model-00002-of-00002.safetensors",
358
- "model.layers.3.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
359
- "model.layers.3.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
360
- "model.layers.3.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
361
- "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
362
- "model.layers.3.mamba.A_log": "model-00001-of-00002.safetensors",
363
- "model.layers.3.mamba.D": "model-00001-of-00002.safetensors",
364
- "model.layers.3.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
365
- "model.layers.3.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
366
- "model.layers.3.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
367
- "model.layers.3.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
368
- "model.layers.3.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
369
- "model.layers.3.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
370
- "model.layers.3.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
371
- "model.layers.3.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
372
- "model.layers.3.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
373
- "model.layers.3.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
374
- "model.layers.3.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
375
- "model.layers.4.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
376
- "model.layers.4.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
377
- "model.layers.4.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
378
- "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
379
- "model.layers.4.mamba.A_log": "model-00001-of-00002.safetensors",
380
- "model.layers.4.mamba.D": "model-00001-of-00002.safetensors",
381
- "model.layers.4.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
382
- "model.layers.4.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
383
- "model.layers.4.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
384
- "model.layers.4.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
385
- "model.layers.4.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
386
- "model.layers.4.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
387
- "model.layers.4.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
388
- "model.layers.4.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
389
- "model.layers.4.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
390
- "model.layers.4.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
391
- "model.layers.4.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
392
- "model.layers.5.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
393
- "model.layers.5.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
394
- "model.layers.5.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
395
- "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
396
- "model.layers.5.mamba.A_log": "model-00001-of-00002.safetensors",
397
- "model.layers.5.mamba.D": "model-00001-of-00002.safetensors",
398
- "model.layers.5.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
399
- "model.layers.5.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
400
- "model.layers.5.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
401
- "model.layers.5.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
402
- "model.layers.5.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
403
- "model.layers.5.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
404
- "model.layers.5.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
405
- "model.layers.5.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
406
- "model.layers.5.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
407
- "model.layers.5.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
408
- "model.layers.5.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
409
- "model.layers.6.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
410
- "model.layers.6.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
411
- "model.layers.6.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
412
- "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
413
- "model.layers.6.mamba.A_log": "model-00001-of-00002.safetensors",
414
- "model.layers.6.mamba.D": "model-00001-of-00002.safetensors",
415
- "model.layers.6.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
416
- "model.layers.6.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
417
- "model.layers.6.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
418
- "model.layers.6.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
419
- "model.layers.6.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
420
- "model.layers.6.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
421
- "model.layers.6.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
422
- "model.layers.6.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
423
- "model.layers.6.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
424
- "model.layers.6.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
425
- "model.layers.6.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
426
- "model.layers.7.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
427
- "model.layers.7.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
428
- "model.layers.7.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
429
- "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
430
- "model.layers.7.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
431
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
432
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
433
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
434
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
435
- "model.layers.8.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
436
- "model.layers.8.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
437
- "model.layers.8.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
438
- "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
439
- "model.layers.8.mamba.A_log": "model-00001-of-00002.safetensors",
440
- "model.layers.8.mamba.D": "model-00001-of-00002.safetensors",
441
- "model.layers.8.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
442
- "model.layers.8.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
443
- "model.layers.8.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
444
- "model.layers.8.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
445
- "model.layers.8.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
446
- "model.layers.8.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
447
- "model.layers.8.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
448
- "model.layers.8.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
449
- "model.layers.8.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
450
- "model.layers.8.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
451
- "model.layers.8.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors",
452
- "model.layers.9.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
453
- "model.layers.9.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
454
- "model.layers.9.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
455
- "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
456
- "model.layers.9.mamba.A_log": "model-00001-of-00002.safetensors",
457
- "model.layers.9.mamba.D": "model-00001-of-00002.safetensors",
458
- "model.layers.9.mamba.b_layernorm.weight": "model-00001-of-00002.safetensors",
459
- "model.layers.9.mamba.c_layernorm.weight": "model-00001-of-00002.safetensors",
460
- "model.layers.9.mamba.conv1d.bias": "model-00001-of-00002.safetensors",
461
- "model.layers.9.mamba.conv1d.weight": "model-00001-of-00002.safetensors",
462
- "model.layers.9.mamba.dt_layernorm.weight": "model-00001-of-00002.safetensors",
463
- "model.layers.9.mamba.dt_proj.bias": "model-00001-of-00002.safetensors",
464
- "model.layers.9.mamba.dt_proj.weight": "model-00001-of-00002.safetensors",
465
- "model.layers.9.mamba.in_proj.weight": "model-00001-of-00002.safetensors",
466
- "model.layers.9.mamba.out_proj.weight": "model-00001-of-00002.safetensors",
467
- "model.layers.9.mamba.x_proj.weight": "model-00001-of-00002.safetensors",
468
- "model.layers.9.pre_ff_layernorm.weight": "model-00001-of-00002.safetensors"
469
- }
470
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
special_tokens_map.json DELETED
@@ -1,45 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|im_start|>",
4
- "<|im_end|>",
5
- "<|object_ref_start|>",
6
- "<|object_ref_end|>",
7
- "<|box_start|>",
8
- "<|box_end|>",
9
- "<|quad_start|>",
10
- "<|quad_end|>",
11
- "<|vision_start|>",
12
- "<|vision_end|>",
13
- "<|vision_pad|>",
14
- "<|image_pad|>",
15
- "<|video_pad|>"
16
- ],
17
- "bos_token": {
18
- "content": "<|startoftext|>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- },
24
- "eos_token": {
25
- "content": "<|im_end|>",
26
- "lstrip": false,
27
- "normalized": false,
28
- "rstrip": false,
29
- "single_word": false
30
- },
31
- "pad_token": {
32
- "content": "<|pad|>",
33
- "lstrip": false,
34
- "normalized": false,
35
- "rstrip": false,
36
- "single_word": false
37
- },
38
- "unk_token": {
39
- "content": "<|unk|>",
40
- "lstrip": false,
41
- "normalized": false,
42
- "rstrip": false,
43
- "single_word": false
44
- }
45
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json DELETED
@@ -1,257 +0,0 @@
1
- {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "add_prefix_space": null,
5
- "added_tokens_decoder": {
6
- "0": {
7
- "content": "<|pad|>",
8
- "lstrip": false,
9
- "normalized": false,
10
- "rstrip": false,
11
- "single_word": false,
12
- "special": true
13
- },
14
- "1": {
15
- "content": "<|startoftext|>",
16
- "lstrip": false,
17
- "normalized": false,
18
- "rstrip": false,
19
- "single_word": false,
20
- "special": true
21
- },
22
- "3": {
23
- "content": "<|unk|>",
24
- "lstrip": false,
25
- "normalized": false,
26
- "rstrip": false,
27
- "single_word": false,
28
- "special": true
29
- },
30
- "518": {
31
- "content": "<|im_start|>",
32
- "lstrip": false,
33
- "normalized": false,
34
- "rstrip": false,
35
- "single_word": false,
36
- "special": true
37
- },
38
- "519": {
39
- "content": "<|im_end|>",
40
- "lstrip": false,
41
- "normalized": false,
42
- "rstrip": false,
43
- "single_word": false,
44
- "special": true
45
- },
46
- "520": {
47
- "content": "<|object_ref_start|>",
48
- "lstrip": false,
49
- "normalized": false,
50
- "rstrip": false,
51
- "single_word": false,
52
- "special": true
53
- },
54
- "521": {
55
- "content": "<|object_ref_end|>",
56
- "lstrip": false,
57
- "normalized": false,
58
- "rstrip": false,
59
- "single_word": false,
60
- "special": true
61
- },
62
- "522": {
63
- "content": "<|box_start|>",
64
- "lstrip": false,
65
- "normalized": false,
66
- "rstrip": false,
67
- "single_word": false,
68
- "special": true
69
- },
70
- "523": {
71
- "content": "<|box_end|>",
72
- "lstrip": false,
73
- "normalized": false,
74
- "rstrip": false,
75
- "single_word": false,
76
- "special": true
77
- },
78
- "524": {
79
- "content": "<|quad_start|>",
80
- "lstrip": false,
81
- "normalized": false,
82
- "rstrip": false,
83
- "single_word": false,
84
- "special": true
85
- },
86
- "525": {
87
- "content": "<|quad_end|>",
88
- "lstrip": false,
89
- "normalized": false,
90
- "rstrip": false,
91
- "single_word": false,
92
- "special": true
93
- },
94
- "526": {
95
- "content": "<|vision_start|>",
96
- "lstrip": false,
97
- "normalized": false,
98
- "rstrip": false,
99
- "single_word": false,
100
- "special": true
101
- },
102
- "527": {
103
- "content": "<|vision_end|>",
104
- "lstrip": false,
105
- "normalized": false,
106
- "rstrip": false,
107
- "single_word": false,
108
- "special": true
109
- },
110
- "528": {
111
- "content": "<|vision_pad|>",
112
- "lstrip": false,
113
- "normalized": false,
114
- "rstrip": false,
115
- "single_word": false,
116
- "special": true
117
- },
118
- "529": {
119
- "content": "<|image_pad|>",
120
- "lstrip": false,
121
- "normalized": false,
122
- "rstrip": false,
123
- "single_word": false,
124
- "special": true
125
- },
126
- "530": {
127
- "content": "<|video_pad|>",
128
- "lstrip": false,
129
- "normalized": false,
130
- "rstrip": false,
131
- "single_word": false,
132
- "special": true
133
- },
134
- "531": {
135
- "content": "<tool_call>",
136
- "lstrip": false,
137
- "normalized": false,
138
- "rstrip": false,
139
- "single_word": false,
140
- "special": false
141
- },
142
- "532": {
143
- "content": "</tool_call>",
144
- "lstrip": false,
145
- "normalized": false,
146
- "rstrip": false,
147
- "single_word": false,
148
- "special": false
149
- },
150
- "533": {
151
- "content": "<|fim_prefix|>",
152
- "lstrip": false,
153
- "normalized": false,
154
- "rstrip": false,
155
- "single_word": false,
156
- "special": false
157
- },
158
- "534": {
159
- "content": "<|fim_middle|>",
160
- "lstrip": false,
161
- "normalized": false,
162
- "rstrip": false,
163
- "single_word": false,
164
- "special": false
165
- },
166
- "535": {
167
- "content": "<|fim_suffix|>",
168
- "lstrip": false,
169
- "normalized": false,
170
- "rstrip": false,
171
- "single_word": false,
172
- "special": false
173
- },
174
- "536": {
175
- "content": "<|fim_pad|>",
176
- "lstrip": false,
177
- "normalized": false,
178
- "rstrip": false,
179
- "single_word": false,
180
- "special": false
181
- },
182
- "537": {
183
- "content": "<|repo_name|>",
184
- "lstrip": false,
185
- "normalized": false,
186
- "rstrip": false,
187
- "single_word": false,
188
- "special": false
189
- },
190
- "538": {
191
- "content": "<|file_sep|>",
192
- "lstrip": false,
193
- "normalized": false,
194
- "rstrip": false,
195
- "single_word": false,
196
- "special": false
197
- },
198
- "539": {
199
- "content": "<tool_response>",
200
- "lstrip": false,
201
- "normalized": false,
202
- "rstrip": false,
203
- "single_word": false,
204
- "special": false
205
- },
206
- "540": {
207
- "content": "</tool_response>",
208
- "lstrip": false,
209
- "normalized": false,
210
- "rstrip": false,
211
- "single_word": false,
212
- "special": false
213
- },
214
- "541": {
215
- "content": "<think>",
216
- "lstrip": false,
217
- "normalized": false,
218
- "rstrip": false,
219
- "single_word": false,
220
- "special": false
221
- },
222
- "542": {
223
- "content": "</think>",
224
- "lstrip": false,
225
- "normalized": false,
226
- "rstrip": false,
227
- "single_word": false,
228
- "special": false
229
- }
230
- },
231
- "additional_special_tokens": [
232
- "<|im_start|>",
233
- "<|im_end|>",
234
- "<|object_ref_start|>",
235
- "<|object_ref_end|>",
236
- "<|box_start|>",
237
- "<|box_end|>",
238
- "<|quad_start|>",
239
- "<|quad_end|>",
240
- "<|vision_start|>",
241
- "<|vision_end|>",
242
- "<|vision_pad|>",
243
- "<|image_pad|>",
244
- "<|video_pad|>"
245
- ],
246
- "bos_token": "<|startoftext|>",
247
- "clean_up_tokenization_spaces": false,
248
- "eos_token": "<|im_end|>",
249
- "extra_special_tokens": {},
250
- "legacy": true,
251
- "model_max_length": 1000000000000000019884624838656,
252
- "pad_token": "<|pad|>",
253
- "spaces_between_special_tokens": false,
254
- "tokenizer_class": "LlamaTokenizerFast",
255
- "unk_token": "<|unk|>",
256
- "use_default_system_prompt": false
257
- }